Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    symbolic notations related to mathematical or statistical variables

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tilde
    -0.79
    rentices
    -0.75
    widetilde
    -0.72
    overline
    -0.71
     truff
    -0.66
    Données
    -0.65
     Bars
    -0.65
    ensuremath
    -0.64
    iyle
    -0.64
     croire
    -0.63
    POSITIVE LOGITS
    tagext
    0.77
     Carney
    0.68
    ckner
    0.67
     Blatt
    0.67
    qrstuvwxyz
    0.66
     Poon
    0.65
     Kiy
    0.65
     Marino
    0.65
    Varint
    0.65
    Kaya
    0.65
    Act Density 0.022%

    No Known Activations